DST is a Decoder-only simultaneous machine translation model, which can conduct policy decision and translation concurrently

Awesome speech/audio LLMs, representation learning, and codec models

Introduction to Speech Processing

This repository implements SummaryMixing, a simpler, faster and much cheaper replacement to self-attention for automatic speech recognition (see: https://arxiv.org/abs/2307.07421). The code is read…

A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.

The repository contains code for the Sense Project. Contains code from reading teh ECG-Sumamry file from Zephyr folder and then processing it with reading glucose file. the code contains all necess…

This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.

Landing page for primehilltop

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

StyleFlow: Attribute-conditioned Exploration of StyleGAN-generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021)

Utilities for transcribing a set of audio files with IBM Watson Speech to Text (STT), then analyzing the error rate of the STT transcription against a known-good transcription

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple

Conditional Generative model (Normalizing Flow) and experimenting style transfer using this model

Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion (Interspeech 2022)